© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12134
    Prev
    Next
    INDEX
    Explanations

    words used to describe elements of software testing

    oai_token-act-pair · gemini-2.0-flash

    Software testing and development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.63
    اریخ
    -0.60
    ArrowToggle
    -0.58
    ">//
    -0.57
     المعيارى
    -0.54
     NDEBUG
    -0.53
    hassee
    -0.52
    ttemberg
    -0.52
    carton
    -0.51
    windowFixed
    -0.51
    POSITIVE LOGITS
    CreateModel
    0.59
     uyar
    0.55
    mahl
    0.54
     soldati
    0.52
     Warning
    0.51
    ContentLoaded
    0.50
     aceptas
    0.49
     vær
    0.49
    ंदीखरीदारी
    0.48
    uspiel
    0.48
    Activations Density 11.559%

    No Known Activations